• Researched and acquired daily, state-wise cases data for India from Jan’20-Jun’21 from Kaggle • Using the scikit library in Python, trained various supervised regression algorithms (e.g., KNN, SVM, Random Forest, etc.), generating models to predict daily positive cases for each state • Improved upon the above predictions using time-series forecasting models (VAR, ARIMA) • Trained an unsupervised learning clustering algorithm (K-Means Clustering) using the ARIMA model parameters to generate clusters of states • Interpreted the resulting clusters generated by the model to map to the real-world scenarios observed during the first and second wave of COVID-19 in India